Microstructure prediction of two-phase titanium alloy during hot forging using artificial neural networks and FE simulation
- 222 Downloads
The microstructural evolution of titanium alloy under isothermal and non-isothermal hot forging conditions was predicted using artificial neural networks (ANN) and finite element (FE) simulation. In the present work, the change in phase volume fraction, grain size, and the volume fraction of dynamic globularization were modelled considering hot working conditions. Initially, an ANN model was developed for steady-state phase volume fraction. The input parameters were the alloy chemical composition (Al, V, Fe, O, and N) and the holding temperature, and the output parameter was the alpha/beta phase volume fraction at steady state. The non-steady state phase volume fraction under non-isothermal conditions was subsequently modelled on the basis of 4 input parameters such as initial specimen temperature, die (or environment) temperature, steady-state phase volume fraction at die (or environment) temperature, and elapsed time during forging. Resulting ANN models were coupled with the FE simulation (DEFORM-3D) in order to predict the variation of phase volume fraction during isothermal and non-isothermal forging. In addition, a grain size variation and a globularization model were developed for hot forging. To validate the predicted results from the models, Ti-6Al-4V alloy was hot-worked at various conditions and then the resulting microstructures were compared with simulated data. Comparisons between model predictions and experimental data indicated that the ANN model holds promise for microstructure evolution in two phase Ti-6Al-4V alloy.
Keywordsartificial neural network Ti alloy phase volume fraction forging
Unable to display preview. Download preview PDF.
- 2.M. J. Donarchie Jr., Titanium-A Technical Guide, 2nd ed., p. 5–11, ASM International (2000).Google Scholar
- 4.G. Terlinde and G. Fischer, Beta titanium alloys, in Christoph Leyens and Manfred Peters (eds). Titanium and Titanium Alloys, p. 37–57, WILEY VCH GmbH & Co. KGaA (2003).Google Scholar
- 5.S. L. Semiatin, V. Seetharaman, I. Weiss, Advances in the Science and Technology of Titanium Alloy Processing (eds., I. Weiss, R. Srinivasan, P. J. Bania, D. Eylon, and S. L. Semiatin), p. 3–73, TMS, Warrendale, USA (1996).Google Scholar
- 8.E. J. Dayhoff, Neural Network Architecture: An Introduction, VNR Press, New York, USA (1990).Google Scholar
- 9.J. M. Zurada, Introduction to Artificial Neural Systems, PWS Publishing Company, Boston, USA (1992).Google Scholar
- 13.R. Castro and L. Seraphin, Mem. Sci. Rev. Metall. 63, 1025 (1966).Google Scholar
- 18.Y. H. Lee, S. I. Hong, and C. S. Lee, Unpublished data, POSTECH, Korea (2004).Google Scholar
- 19.R. Boyer, G. Welsch, and E. W. Collings, Material Properties Handbook: Titanium Alloys, ASM International, Materials Park, OH 44073 (1994).Google Scholar
- 24.C. H. Park, Y. G. Ko, and C. S. Lee, The 20 th Conference on Mechanical Behaviours of Materials, Korea Institute of Metals and Materials, Korea (2006).Google Scholar
- 28.D. S. Fields and W. A. Backofen, Proc. ASTM 57, 1259 (1957).Google Scholar